Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/luiseiman/dotforge/diff-projectnpx skills add luiseiman/dotforge --skill diff-projectgit clone --depth 1 https://github.com/luiseiman/dotforgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00025 | $0.00651 |
| Opus 5 | $0.00013 | $0.00326 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
diff-project scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diff Project
Show what changed in dotforge since the last synchronization of the current project.
Step 1: Identify project baseline
- Read
$DOTFORGE_DIR/registry/projects.yml - Find the current project by
path(compare with$PWD) - Get
dotforge_versionandlast_sync - If no
dotforge_versionis registered (null), report:
And stop.Project not synced — no baseline to compare against. Run /forge sync to establish baseline.
Step 2: Verify local manifest
If .claude/.forge-manifest.json exists in the current project:
- Read it and get the version and file hashes
- For each file in the manifest, calculate
shasum -a 256 <file> | cut -d' ' -f1 - Compare against the registered hash
- Report locally modified files (hash differs) and deleted files
- Use the manifest version as baseline (more precise than the registry)
If manifest does NOT exist, continue to Step 3 using git log.
Step 3: Detect changes in dotforge
Run in $DOTFORGE_DIR/:
git log --oneline v<version>..HEAD -- template/ stacks/
Where <version> is the tag corresponding to the project's dotforge_version.
If the tag does not exist, use last_sync as reference:
git log --oneline --since="<last_sync>" -- template/ stacks/
If there are no relevant commits, report:
dotforge has no changes in template/stacks since v<version>.
Project is up to date.
Step 4: Show change summary
For each modified file in template/ or relevant stacks/ for the project:
═══ DIFF dotforge: v<previous> → v<current> ═══
Project: <name> (last sync: <date>)
Files modified in dotforge:
template/hooks/block-destructive.sh — <diff summary>
template/rules/_common.md — <diff summary>
stacks/python-fastapi/rules/backend.md — <diff summary>
Local files with modifications (vs manifest):
.claude/rules/_common.md — hash differs from deployed
Filter stacks/ to show only the stacks used by the project (read from registry).
Step 5: Recommend action
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 91 lines · 25 tokens per session scan A b177698e1fe7
diff-project is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 651 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scaffold
Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
find-opps
Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…